Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx agentmods add skills/jessinra/lorekeeper/after-changesnpx skills add Jessinra/Lorekeeper --skill after-changesgit clone --depth 1 https://github.com/Jessinra/LorekeeperWhat it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5 | $0.00085 | $0.00559 |
| Opus 5 | $0.00043 | $0.00280 |
| Sonnet 5 | $0.00017 | $0.00112 |
| Haiku 4.5 | $0.00009 | $0.00056 |
Grade A, and why
after-changes scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
What it actually says
After-Changes Checklist
Run these three steps in sequence after every set of code changes.
Step 1 — Code Review
Run the /simplify skill. Wait for it to complete and apply all fixes before moving on.
Step 2 — README Check
- Run
git diff HEAD(orgit diff HEAD~1if already staged/committed) to get the full list of changed files and what changed. - Read
README.md. - For each changed file, check: does the README make a claim about this file, its API, its behaviour, or its config that is now stale?
- Common staleness patterns:
- New env vars / config keys not in the config table
- API endpoints added, removed, or renamed
- New UI tabs, features, or workflows not described
- Architecture claims that no longer match the code
- "Cannot do X" statements that are now wrong
- If anything is stale or missing, update
README.mdin-place. Keep changes minimal — add what's missing, fix what's wrong, remove nothing that's still true. - If README is already accurate, say so and skip.
Step 3 — Commit
-
Run
git statusandgit diff HEADto review everything that will be committed. -
Stage all relevant changed files (be explicit — avoid
git add -A). -
Write a commit message following this format:
<type>(<scope>): <short summary under 72 chars> - bullet for each logical change - explain WHY for non-obvious changes Co-Authored-By: Claude Sonnet 4.6 <[email protected]>Types:
feat,fix,refactor,docs,chore,test -
Confirm the commit hash and summary.
Notes
- If Step 1 (simplify) finds and fixes issues, re-check README in Step 2 for any new staleness those fixes introduced.
- If there is nothing to commit (working tree clean), say so and stop.
- Do not push — only commit locally unless the user explicitly asks to push.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 2d ago First seen · 52 lines · 0 tokens per session scan A e461bb37ab42
after-changes is a skill published in the GitHub repository Jessinra/Lorekeeper (4 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 85 tokens to every session and 559 once invoked, about $0.0004 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
commit
Atomic git commit with conventional message. Use when the user says "commit", "save my changes", "commit this", or wants to create a git commit. Stages specific files, writes a conventional commit message with body explaining non-obvious decisions. Never uses git add -A.
commitlore-commits
Use when about to make a git commit and there is decision context worth recording — a constraint that shaped the change, an alternative that was tried and dropped, a warning for whoever touches this next. Drives the CommitLore capture pipeline, which drafts a record from the session transcript and the staged diff…
commitlore-setup
Use when a git repository needs CommitLore wired up for the first time, or when its hook/notes configuration looks broken. Runs the diagnostic, installs the commit-msg validation hook, fixes the notes fetch refspec so records survive a clone or fetch, and builds the local record index. Trigger phrases include "set up…
commitlore-codex
Use when reading or changing a repository would benefit from its recorded decision history, or when a commit may need verified decision context. Query before edits, guard against previously rejected approaches, and capture supported records before committing.
commitlore-commits
Capture a decision record from verified session and diff evidence before a commit.
commitlore-setup
Set up CommitLore in a repository when the operator asks for it.